ntvНаучно-технический вестник информационных технологий, механики и оптикиScientific and Technical Journal of Information Technologies, Mechanics and Optics2226-14942500-0373Университет ИТМО10.17586/2226-1494-2025-25-6-1185-1196ntv-552Research ArticleМАТЕМАТИЧЕСКОЕ И КОМПЬЮТЕРНОЕ МОДЕЛИРОВАНИЕMODELING AND SIMULATIONDeFs-CBDE: бинарная мутация, управляемая кластеризацией, в многокритериальной дифференциальной эволюции для отбора генов с помощью микрочиповDeFs-CBDE: Clustering-guided binary mutation in multi-objective differential evolution for microarray gene selectionhttps://orcid.org/0009-0009-5775-7956Джеллаль СерандиМ.Djellal SerandiM.

Мохамед Джеллаль Серанди, аспирант

Лаборатория LISYS

29000; Маскара

Mohamed Djellal Serandi, PhD Student

LISYS laboratory

29000; Mascara

mohamed.djellalserandi@univ-mascara.dzhttps://orcid.org/0000-0002-5733-586XБуфераФ.BouferaF.

Фатма Буфера, кандидат технических наук, профессор, профессор кафедры

Лаборатория LISYS

29000; Маскара

Fatma Boufera, PhD, Full Professor

LISYS laboratory

29000; Mascara

fboufera@univ-mascara.dzhttps://orcid.org/0000-0002-3628-7483ХуариА.HouariA.

Амина Хуари, PhD, доцент

Лаборатория LISYS

29000; Маскара

sc 57021480300

Amina Houari, PhD, Associate Professor

LISYS laboratory

29000; Mascara

sc 57021480300

amina.houari@univ-mascara.dzhttps://orcid.org/0000-0002-2480-2580ФлиттиФ.FlittiF.

Фарид Флитти, PhD, доцент

500001; Дубай

sc 24821958500

Farid Flitti, PhD, Associate Professor

500001; Dubai

sc 24821958500

fflitti@hct.ac.aeУниверситет Мустафы СтамбулиАлжирUniversity Mustapha StambouliAlgeriaВысший колледж технологии, колледж в ДубаеОбъединенные Арабские ЭмиратыHigher Colleges of Technology in DubaiUnited Arab Emirates20252312202525611851196Copyright © Джеллаль Серанди М., Буфера Ф., Хуари А., Флитти Ф., 20252025Джеллаль Серанди М., Буфера Ф., Хуари А., Флитти Ф.Djellal Serandi M., Boufera F., Houari A., Flitti F.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://ntv.elpub.ru/jour/article/view/552

   Технология ДНК-микрочипов позволяет получать высокоразмерные данные об экспрессии генов, многие из которых не имеют отношения к заболеванию. Эффективный отбор признаков, таким образом, необходим для смягчения «проклятия размерности» и повышения эффективности классификации. В данном исследовании представлен многокритериальный подход к отбору признаков с использованием мутации на основе кластеризации для идентификации компактного набора генов, связанных с заболеванием. Предложенный алгоритм DeFs-CBDE был оценен на четырех наборах данных об экспрессии генов: рак головного мозга, молочной железы, легких и центральной нервной системы, путем отбора информативных подмножеств признаков и их оценки с использованием пяти современных классификаторов, а именно: метода опорных векторов, наивного байесовского алгоритма, метода K-ближайших соседей, дерева решений и случайного леса. Метод DeFs-CBDE достиг 100 % точности на наборе данных о мозге с тремя классификаторами. В наборе данных по легким DeFs-CBDE достиг точности 97,56 % с использованием метода опорных векторов и дерева решений. В наборе данных по молочной железе DeFs-CBDE достиг точности 93,33 %, что очень близко к максимальному результату в 93,81 %. Набор данных по центральной нервной системе оказался самым сложным, где точность составила 91,67 % с использованием. Во всех наборах данных DeFs-CBDE стабильно демонстрировал высокую эффективность классификации.

   DNA microarray technology produces high-dimensional gene expression data, where many genes are irrelevant to disease. Effective feature selection is thus essential to mitigate the curse of dimensionality and enhance classification performance. This study introduces a multi-objective feature selection approach employing a Clustering-Based Binary Differential Evolution (CBDE) mutation to identify a compact set of disease-relevant genes. The proposed DeFs-CBDE algorithm was assessed on four gene expression datasets, i.e. brain, breast, lung, and central nervos system cancer by selecting informative feature subsets and evaluating them using five state-of-the-art classifiers, i.e., Support Vector Machine (SVM), Naive Bayes, K-Nearest Neighbors, Decision Tree (DT), and Random Forest. The DeFs-CBDE method achieved of 100 % accuracy on the brain dataset with three classifiers. On the lung dataset, DeFs-CBDE reached 97.56 % accuracy with SVM and DT. For the breast dataset, DeFs-CBDE attained 93.33 % accuracy very close to the highest score of 93.81 % accuracy. The CNS dataset proved the most challenging, where it achieved 91.67 % accuracy with SVM. Across all datasets, DeFs-CBDE consistently achieved high classification performance.

данные микрочиповвыбор признаковоптимизациядифференциальная эволюциямутациямногокритериальный анализmicroarray datafeature selectionoptimizationdifferential evolutionmutationmulti-objectiveReferencesTrunk G.V. A problem of dimensionality: A simple example // IEEE Transactions on Pattern Analysis and Machine Intelligence. 1979. V. PAMI-1. N 3. P. 306–307. doi: 10.1109/tpami.1979.4766926Trunk G.V. A problem of dimensionality: A simple example. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1979, vol. PAMI-1, no. 3, pp. 306–307. doi: 10.1109/tpami.1979.4766926Sab eri-Movahed F., Rostami M., Berahmand K., Karami S., Tiwari P., Oussalah M., Band S.S. Dual regularized unsupervised feature selection based on matrix factorization and minimum redundancy with application in gene selection // Knowledge-Based Systems. 2022. V. 256. P. 109884. doi: 10.1016/j.knosys.2022.109884Saberi-Movahed F., Rostami M., Berahmand K., Karami S., Tiwari P., Oussalah M., Band S.S. Dual regularized unsupervised feature selection based on matrix factorization and minimum redundancy with application in gene selection. Knowledge-Based Systems, 2022, vol. 256 pp. 109884. doi: 10.1016/j.knosys.2022.109884Deb K. Multi-objective optimisation using evolutionary algorithms: an introduction // Multi-objective Evolutionary Optimisation for Product Design and Manufacturing. 2011. P. 3–34.Deb K. Multi-objective optimisation using evolutionary algorithms: an introduction. Multi-objective Evolutionary Optimisation for Product Design and Manufacturing, 2011, pp. 3–34.Che ng Y., Church G.M. Biclustering of expression data // Proc. of the 8<sup>th</sup> International Conference on Intelligent Systems for Molecular Biology. 2000. P. 93–103.Cheng Y., Church G.M. Biclustering of expression data. Proc. of the 8<sup>th</sup> International Conference on Intelligent Systems for Molecular Biology, 2000, pp. 93–103.Zha ng Y., Gong D., Gao X., Tian T., Sun X. Binary differential evolution with self-learning for multi-objective feature selection // Information Sciences. 2020. V. 507. P. 67–85. doi: 10.1016/j.ins.2019.08.040Zhang Y., Gong D., Gao X., Tian T., Sun X. Binary differential evolution with self-learning for multi-objective feature selection. Information Sciences, 2020, vol. 507, pp. 67–85. doi: 10.1016/j.ins.2019.08.040Ali W., Saeed F. Hybrid filter and genetic algorithm-based feature selection for improving cancer classification in high-dimensional microarray data // Processes. 2023. V. 11. N 2. P. 562. doi: 10.3390/pr11020562Ali W., Saeed F. Hybrid filter and genetic algorithm-based feature selection for improving cancer classification in high-dimensional microarray data. Processes, 2023, vol. 11, no. 2, p. 562. doi: 10.3390/pr11020562Aha dzadeh B., Abdar M., Safara F., Khosravi A., Menhaj M.B., Suganthan P.N. SFE: A simple, fast, and efficient feature selection algorithm for high-dimensional data // IEEE Transactions on Evolutionary Computation. 2023. V. 27. N 6. P. 1896–1911. doi: 10.1109/tevc.2023.3238420Ahadzadeh B., Abdar M., Safara F., Khosravi A., Menhaj M.B., Suganthan P.N. SFE: A simple, fast, and efficient feature selection algorithm for high-dimensional data. IEEE Transactions on Evolutionary Computation, 2023, vol. 27, no. 6, pp. 1896–1911. doi: 10.1109/tevc.2023.3238420Prajapati S., Das H., Gourisaria M.K. Feature selection using differential evolution for microarray data classification // Discover Internet of Things. 2023. V. 3. N 1. P. 12. doi: 10.1007/s43926-023-00042-5Prajapati S., Das H., Gourisaria M.K. Feature selection using differential evolution for microarray data classification. Discover Internet of Things, 2023. vol. 3, no. 1, p. 12. doi: 10.1007/s43926-023-00042-5Hamla H., Ghanem K. A hybrid feature selection based on fisher score and svm-rfe for microarray data // Informatica. 2024. V. 48. N 1. P. 57–68. doi: 10.31449/inf.v48i1.4759Hamla H., Ghanem K. A hybrid feature selection based on fisher score and svm-rfe for microarray data. Informatica, 2024, vol. 48, no. 1, pp. 57–68. doi: 10.31449/inf.v48i1.4759Pau l D., Jain A., Saha S., Mathew J. Multi-objective pso based online feature selection for multi-label classification // Knowledge-Based Systems. 2021. V. 222. P. 106966, doi: 10.1016/j.knosys.2021.106966Paul D., Jain A., Saha S., Mathew J. Multi-objective pso based online feature selection for multi-label classification. Knowledge-Based Systems, 2021, vol. 222, pp. 106966, doi: 10.1016/j.knosys.2021.106966Han F., Chen W.-T., Ling Q.-H., Han H. Multi-objective particle swarm optimization with adaptive strategies for feature selection // Swarm and Evolutionary Computation. 2021. V. 62. P. 100847. doi: 10.1016/j.swevo.2021.100847Han F., Chen W.-T., Ling Q.-H., Han H. Multi-objective particle swarm optimization with adaptive strategies for feature selection. Swarm and Evolutionary Computation, 2021, vol. 62, pp. 100847. doi: 10.1016/j.swevo.2021.100847Das htban M., Balafar M., Suravajhala P. Gene selection for tumor classification using a novel bio-inspired multi-objective approach // Genomics. 2018. V. 110. N 1. P. 10–17. doi: 10.1016/j.ygeno.2017.07.010Dashtban M., Balafar M., Suravajhala P. Gene selection for tumor classification using a novel bio-inspired multi-objective approach. Genomics, 2018, vol. 110, no. 1, pp. 10–17. doi: 10.1016/j.ygeno.2017.07.010Gho sh M., Adhikary S., Ghosh K.K., Sardar A., Begum S., Sarkar R. Genetic algorithm based cancerous gene identification from microarray data using ensemble of filter methods // Medical and Biological Engineering and Computing. 2019. V. 57. N 1. P. 159–176. doi: 10.1007/s11517-018-1874-4Ghosh M., Adhikary S., Ghosh K.K., Sardar A., Begum S., Sarkar R. Genetic algorithm based cancerous gene identification from microarray data using ensemble of filter methods. Medical and Biological Engineering and Computing, 2019, vol. 57, no. 1, pp. 159–176. doi: 10.1007/s11517-018-1874-4St orn R., Price K. Differential evolution: a simple and efficient adaptive scheme for global optimization over continuous spaces // International Computer Science Institute. 1995. V. 95. N 12. P. 1–12.Storn R., Price K. Differential evolution: a simple and efficient adaptive scheme for global optimization over continuous spaces. International Computer Science Institute, 1995, vol. 95, no. 12, pp. 1–12.Cha rfaoui Y., Houari A., Boufera F. AMoDeBic: An adaptive multi-objective differential evolution biclustering algorithm of microarray data using a biclustering binary mutation operator // Expert Systems with Applications. 2024. V. 238. Part B. P. 121863, doi: 10.1016/j.eswa.2023.121863Charfaoui Y., Houari A., Boufera F. AMoDeBic: An adaptive multi-objective differential evolution biclustering algorithm of microarray data using a biclustering binary mutation operator. Expert Systems with Applications, 2024, vol. 238, part B, pp. 121863, doi: 10.1016/j.eswa.2023.121863Gol dberg D.E. Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, 1989. 412 p.Goldberg D.E. Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, 1989, 412 p.Deb K., Pratap A., Agarwal S., Meyarivan T. A fast and elitist multi-objective genetic algorithm: NSGA-II // IEEE Transactions on Evolutionary Computation. 2002. V. 6. N 2. P. 182–197. doi: 10.1109/4235.996017Deb K., Pratap A., Agarwal S., Meyarivan T. A fast and elitist multi-objective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 2002, vol. 6, no. 2, pp. 182–197. doi: 10.1109/4235.996017Nor onha M.D., Henriques R., Madeira S.C., Zárate L.E. Impact of metrics on biclustering solution and quality : a review // Pattern Recognition. 2022. V. 127. P. 108612. doi: 10.1016/j.patcog.2022.108612Noronha M.D., Henriques R., Madeira S.C., Zárate L.E. Impact of metrics on biclustering solution and quality : a review. Pattern Recognition, 2022, vol. 127, pp. 108612. doi: 10.1016/j.patcog.2022.108612Pom eroy S.L., Tamayo P., Gaasenbeek M., Sturla L.M., Angelo M., McLaughlin M.E., et al. Prediction of central nervous system embryonal tumour outcome based on gene expression // Nature. 2002. V. 415. N 6870. P. 436–442. doi: 10.1038/415436aPomeroy S.L., Tamayo P., Gaasenbeek M., Sturla L.M., Angelo M., McLaughlin M.E., et al. Prediction of central nervous system embryonal tumour outcome based on gene expression. Nature, 2002, vol. 415, no. 6870, pp. 436–442. doi: 10.1038/415436avan ’t Veer L.J., Dai H., van de Vijver M.J., He Y.D., Hart A.A.M., Mao M., et al. Gene expression profiling predicts clinical outcome of breast cancer // Nature. 2002. V. 415. N 6871. P. 530–536. doi: 10.1038/415530avan’t Veer L.J., Dai H., van de Vijver M.J., He Y.D., Hart A.A.M., Mao M., et al. Gene expression profiling predicts clinical outcome of breast cancer. Nature, 2002, vol. 415, no. 6871, pp. 530–536. doi: 10.1038/415530aZha o G., Wu Y. Feature subset selection for cancer classification using weight local modularity // Scientific Reports. 2016. V. 6. P. 34759. doi: 10.1038/srep34759Zhao G., Wu Y. Feature subset selection for cancer classification using weight local modularity. Scientific Reports, 2016, vol. 6, pp. 34759. doi: 10.1038/srep34759Kolberg L., Raudvere U., Kuzmin I., Adler P., Vilo J., Peterson H. g.: Profiler—interoperable web service for functional enrichment analysis and gene identifier mapping (2023 update) // Nucleic Acids Research. 2023. V. 51. N W1. P. W207–W212. doi: 10.1093/nar/gkad347Kolberg L., Raudvere U., Kuzmin I., Adler P., Vilo J., Peterson H. g: Profiler—interoperable web service for functional enrichment analysis and gene identifier mapping (2023 update). Nucleic Acids Research, 2023, vol. 51, no. W1, pp. W207–W212. doi: 10.1093/nar/gkad347Herbst R.S., Morgensztern D., Boshoff C. The biology and management of non-small cell lung cancer // Nature. 2018. V. 553. N 7689. P. 446–454. doi: 10.1038/nature25183Herbst R.S., Morgensztern D., Boshoff C. The biology and management of non-small cell lung cancer. Nature, 2018, vol. 553, no. 7689, pp. 446–454. doi: 10.1038/nature25183Skoulidis F., Heymach J.V. Co-occurring genomic alterations in non-small-cell lung cancer biology and therapy // Nature Reviews Cancer. 2019. V. 19. N 9. P. 495–509. doi: 10.1038/s41568-019-0179-8Skoulidis F., Heymach J.V. Co-occurring genomic alterations in non-small-cell lung cancer biology and therapy. Nature Reviews Cancer, 2019, vol. 19, no. 9, pp. 495–509. doi: 10.1038/s41568-019-0179-8Nath S., Mukherjee P. Muc1: a multifaceted oncoprotein with a key role in cancer progression // Trends in Molecular Medicine. 2014. V. 20. N 6. P. 332–342. doi: 10.1016/j.molmed.2014.02.007Nath S., Mukherjee P. Muc1: a multifaceted oncoprotein with a key role in cancer progression. Trends in Molecular Medicine, 2014, vol. 20, no. 6, pp. 332–342. doi: 10.1016/j.molmed.2014.02.007

The authors declare that there are no conflicts of interest present.